Salesforce Agentforce Real-Time Project Implementation

Explore how to build a 24/7 hotel assistant with Agent Force, integrating Rumi for bookings, room service, food orders, and checkout in Salesforce using reusable actions and flows.

Create an agent force enabled developer org and deploy customer, food options, and food bill. Clone repo and deploy with Salesforce CLI and VS Code to initialize Luke's hotel app.

Enable digital experience, create a public guest site named Rumi, and set up Einstein service user as the roomie agent. Publish the site and tailor the welcome message and topics.

Deploy the Roomie agent to the public site by configuring omni-channel routing, a messaging channel, and embedded service deployment, then test via the preview and enhanced web chat.

In this lesson, the agent creates a customer record via a flow action, passing name, mobile number, check-in date, and room preference, and returns a unique customer ID for onboarding.

Design a deterministic agent script framework with an active flow gate to lock context and prevent hallucinations in hotel room booking, using topic selectors, variables, and explicit transitions.

Breaks a large hotel room booking topic into two well defined topics and enables topic chaining through action invocation to generate a customer ID and confirm bookings.

Develop and deploy a receptionist employee agent that initiates customer check-in by obtaining a customer ID and updating the Salesforce status to checked in, enabling future service workflows.

Design a food booking module for the Roomie agent with customer, food options, items, and bills. Add a validation flow for guest customers to confirm IDs on first contact.

Adds a food booking flow that verifies customers by ID against Salesforce, using an auto-launch validate customer action and an active flow to ensure only verified, checked-in customers proceed.

Validate the customer, present all food options via a custom action, then show options in a tabular format and proceed to create food items and a bill using option IDs.

Build an Apex custom action to process dynamic food orders from a Rumi agent by deserializing JSON of item IDs and quantities, creating a customer-linked food bill and items.

Demonstrates completing a food booking by invoking a process food order apex invocable method, converting user selections to JSON, creating a food bill, and linking it to the customer.

Learn to implement sequential action chaining with agent script, linking a generated food bill to a customer via a follow-up action that updates records and confirms the order.

Implement end to end room service by creating a linked Salesforce case assigned to a room service queue, validating customers, and initiating service requests through a configurable topic flow.

Rumi guides customers from onboarding to checkout, calculating and displaying a line-by-line bill breakdown, instructing payment at the reception, returning keys, and updating Salesforce status to checkout.

Deploy an lwc component to recreate the hotel loox ui on a customer site, using cursor ai assistant and copilot to speed up front-end development in experience cloud.

Explore building a Salesforce Einstein AI powered clinical trial agent using service agents, data triggered workflows, and data cloud libraries to answer FAQs, recommend trials, and automate post-enrollment tasks.

Enable data cloud to power the clinical research agent, connect to a FAQ PDF knowledge base, and create the clinical research app with a front-end agent and data library.

Create and deploy the Agent Force data library for faq documents, upload clinical trials pdfs, and configure a data cloud retriever to power agent answers via prompt templates.

Upload a clinical trials PDF to a new data library, extract eligibility criteria with data cloud rag and agent force, test prompts, and match patients to trials via a retriever.

Create a knowledge prompt template to enable a clinical trial agent to retrieve trials from a PDF data library, filter by patient age, city, gender, and condition, and present matches.

Create a new participant-facing community site, deploy the front-end clinical research agent, and configure an omnichannel flow with a messaging channel to route work via the logged-in patient context.

Enable person accounts to create participant site users. Log in as the user to access patient data such as city and age for real-time agent queries.

Publish the logged-in user ID from the community page, populate a pre-chat field, and use an omnichannel flow to stamp the messaging session with the current account for the agent.

Create a flow action that builds a dynamic prompt from the current patient details via session context, then passes it to the clinical trial recommendation prompt and displays results.

enroll participants in clinical trials by adding a trial enrollment object and a flow-driven action that links participants to trials via a junction record.

Create and manage a clinical trial activities data library in Salesforce Data Cloud; build an agent that retrieves activities from PDFs, automates task creation and Slack alerts for each study.

Create a backend post enrollment agent separate from the front-end clinical trial agent to manage backend activities with a prompt template and data library.

Build flow actions to create task records linked to participants and to send Slack messages, supported by a clinical trial queue and a prompt template that fetches activities.

Implement real-time Slack notifications from Salesforce by creating a custom Apex invocable action using incoming webhooks, remote site settings, and a Slack app to notify on new trial participant enrollments.

Create a record-triggered flow on enrollment that invokes the post enrollment agent after a delay, passing participant id and clinical trial name to trigger activities and slack messages.

Update the medicore research site UI to resemble a clinical research site, enable read, typing, and delivery receipts, and publish the embedded service deployment with the clinical research header.

Install and configure Java, set environment variables, and verify with the Java version. Then install the Salesforce CLI, VS Code, Git, and the Salesforce Extension Pack for VS Code.